The field of handwritten text recognition is moving towards more realistic and challenging scenarios, such as recognizing multi-digit numbers and texts in low-resource languages. Researchers are leveraging knowledge about writers and developing new benchmarks to improve performance in real-world settings. Innovative methods, such as leveraging task-specific knowledge and using hybrid architectures, are being proposed to advance the field. Noteworthy papers include:

• A Fine Evaluation Method for Cube Copying Test for Early Detection of Alzheimer's Disease, which proposes a fine evaluation method for early screening and personalized intervention of visual spatial cognitive impairment.
• Handwritten Text Recognition for Low Resource Languages, which introduces a novel segmentation-free paragraph-level handwritten text recognition model for low-resource languages.